Modelling of Fuzzy Logic Based System for the Implementation of Model for Healthcare System with Accurate Prediction

Budgetary restrictions force healthcare institutions to endure ongoing deterioration, which calls for better building capital deterioration modeling. A more sophisticated predictive model is essential to implementing a proactive maintenance approach and lowering unexpected failures. Hospitals now make subjective deterioration estimates based just on an individual’s age, which creates uncertainty. This research addresses the shortcomings of existing approaches by putting forward a novel stochastic degradation prediction model. The model, a fuzzy Markovian technique based on hybrid genetic algorithms, reduces subjectivity by anticipating based on the most recent observed circumstances. The model uses a nonhomogeneous transition matrix of probabilities (TPM) with fuzzy membership functions of condition, maturity, and relative degradation rate due to the paucity of data on the condition evaluation of important infrastructure. Genetic algorithm calibration improves TPM accuracy by addressing the limitations of expert-based models. A sensitivity analysis checks for changes in output when parameters are changed, ensuring the resilience of the model. Real hospital datasets are used for validation against a cutting-edge stochastic model, and the results show improved performance over existing approaches. In order to provide the best possible administration of healthcare facilities, this approach offers to assist decision-makers in creating effective maintenance of data-driven capital renewal strategies.